INDEX

Explanations

references to plots in storytelling contexts

oai_token-act-pair · gpt-3.5-turbo

references to "plot" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IDA

-0.74

agles

-0.71

Downloadha

-0.69

ĪĴ

-0.66

Scot

-0.64

INTON

-0.63

angelo

-0.62

Sales

-0.62

 Jazz

-0.60

conservancy

-0.59

POSITIVE LOGITS

ters

0.86

 Plot

0.81

 twists

0.81

 synopsis

0.78

 Thick

0.77

line

0.76

lines

0.76

 plot

0.74

 twist

0.74

ories

0.74

Activations Density 0.018%

references to plots in storytelling contexts

references to "plot" in various contexts

No Comments

No Known Activations